Deep learning-based explainable target classification for synthetic aperture radar images

Abstract

—Deep learning has been extensively useful for its \nability to mimic the human brain to make decisions. It is able \nto extract features automatically and train the model for classification and regression problems involved with complex images \ndatabases. This paper presents the image classification using \nConvolutional Neural Network (CNN) for target recognition using \nSynthetic-aperture Radar (SAR) database along with Explainable \nArtificial Intelligence (XAI) to justify the obtained results. In this \nwork, we experimented with various CNN architectures on the \nMSTAR dataset, which is a special type of SAR images. Accuracy \nof target classification is almost 98.78% for the underlying preprocessed MSTAR database with given parameter options in \nCNN. XAI has been incorporated to explain the justification \nof test images by marking the decision boundary to reason the \nregion of interest. Thus XAI based image classification is a robust \nprototype for automatic and transparent learning system while \nreducing the semantic gap between soft-computing and humans \nway of perception.